Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/yonatangross/orchestkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/yonatangross/orchestkit/page-serve)<a href="https://agentmods.dev/commands/yonatangross/orchestkit/page-serve"><img src="https://agentmods.dev/badge/commands/yonatangross/orchestkit/page-serve/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/yonatangross/orchestkit/page-serve"><img src="https://agentmods.dev/badge/commands/yonatangross/orchestkit/page-serve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00111 | $0.01421 |
| Opus 5 | $0.00056 | $0.00711 |
| Sonnet 5 | $0.00022 | $0.00284 |
| Haiku 4.5 | $0.00011 | $0.00142 |
Grade A, and why
page-serve scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `<path> [flags]` | `scripts/serve.sh` | prerequisites, server, alias, state, curl check, optional screenshot | How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-generated from skills/page-serve/SKILL.md
Source: https://github.com/yonatangross/orchestkit
/ork:page-serve, give a human a URL
An agent that renders a page for a human needs a way to hand it over. The pattern
that grew in sessions was python3 -m http.server 8991 plus portless alias <name> 8991
typed by hand: no record of the process, no stop, servers outliving the session,
and one measured night (2026-09-06) where the same session did it twice and the
server was still up the next morning. This skill is that pattern with a state file,
a stop, a status, and a loud failure when the URL contract cannot be met.
The contract
- The URL is
https://<name>.localhost/<file>. No port, ever. portless's 443 service owns the port; a:1355or:8991in the URL is the pre-service fallback and the skill refuses rather than emit one. - One static server per name, on a free loopback port, rooted at the file's directory (so sibling assets resolve) or at the directory you pass.
- State in
.claude/state/page-serve/<name>.json: root, file, port, pid, url, time.statusre-measures pid, route, and HTTP on every call; it never trusts the file. - Idempotent per name: same name + same root reuses the live server; a different root
replaces it;
--forceon the alias overrides a stale route with the same name.
Usage
/ork:page-serve docs/playgrounds/roadmap-2026-09-07.html
/ork:page-serve docs/playgrounds/ --name playgrounds
/ork:page-serve <path> --screenshot # agent-browser, returns the png path
/ork:page-serve status [--json]
/ork:page-serve stop <name>
/ork:page-serve stop --all
serve.sh prints url=, name=, port=, pid=, http=, optional screenshot=,
and the exact stop= line to paste. Put the url= line in your reply's Open section.
Modes
| Invocation | Script | What happens |
|---|---|---|
<path> [flags] |
scripts/serve.sh |
prerequisites, server, alias, state, curl check, optional screenshot |
status [--json] |
scripts/status.sh |
one line per served page: server up/dead, route registered/missing, HTTP code |
stop <name> or stop --all |
scripts/stop.sh |
alias removed, server killed, state and screenshot deleted; every step reports |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 102 lines · 111 tokens per session scan A 7a67cda1aa28
page-serve is a command published in the GitHub repository yonatangross/orchestkit (231 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 1,421 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other commands, from other repositories
design-tokens
Définition Design Tokens.
pn-frontend-redo
Audit-driven frontend remediation on an existing app — baseline audit, slice plan, sequential UI slices with maker-checker gates, preflight, deliver. Use instead of pn-program for same-repo sequential surfaces (Home → fight → chrome). Not for greenfield (pn-design) or parallel vertical slices (pn-program).
pn-audit-a11y
Surgical frontend accessibility audit — WCAG contrast, keyboard navigation, ARIA roles, focus management, and screen-reader compatibility. Standalone or chained by pn-frontend-audit.
ui-ux-behaviour-block
When this command is used, use the following block. Acknowledge your understanding and then await the user's request.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.